CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

beautiful-prose

A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is beautiful-prose in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable style contract with concrete bans, control tags, examples, and an explicit self-check workflow. Its main structural flaw is a dangling reference to references/test-cases.md, plus mild redundancy across the prohibition, quality-bar, and lint sections.

Suggestions

Create references/test-cases.md or remove the "Tests" section: the body's only external pointer currently resolves to nothing, which breaks the skill's navigation and its advertised test coverage.

Consolidate the overlapping "Absolute prohibitions", "Quality bar", and "Lint checklist" sections, which restate the same bans three times; a single authoritative ban list plus the lint checklist would cut tokens without losing guidance.

Add one short good/bad example pair per register (e.g., a two-sentence cold_steel vs literary_modern sample) so register selection is grounded in concrete output rather than adjectives alone.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and never explains known concepts; the only over-explanation is that the bans are restated three times across "Absolute prohibitions", "Quality bar", and "Lint checklist", which is minor enough for anchor 4 rather than the perfectly lean anchor 5.

4 / 5

Actionability

Fully actionable for an instruction-only skill: exhaustive banned-phrase lists, explicit control tags (REGISTER, DENSITY, HEAT, LENGTH) with a complete invocation example, concrete positive constraints, and good/bad example pairs covering the common failure modes, matching anchor 5.

5 / 5

Workflow Clarity

As a single-purpose skill the action is unambiguous: activate on request, apply the constraints, then the explicit pre-finalize check ("Before finalizing, check internally") and the fail-condition lint checklist provide a clear validation checkpoint, so the simple-skill exception for anchor 5 applies.

5 / 5

Progressive Disclosure

Sections are well organized with clear headers, but the body's only external reference ("See references/test-cases.md") points to a file that does not exist in the bundle (no references/ directory), breaking navigation and capping this at anchor 3 rather than 4.

3 / 5

Total

17

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly and explicitly states both what the skill does and when to use it, with a distinctive anti-AI-tic framing and mostly natural trigger terms. It could list its concrete capabilities more specifically and cover a few more natural synonyms users would say.

Suggestions

Enumerate the concrete capabilities more specifically (e.g., drafting new prose, rewriting user-supplied text, enforcing a lint pass on output) instead of the single implied "prose or rewrites" action.

Add common natural trigger synonyms users would actually say, such as "writing", "editing", "make this sound less AI", or "tighten this draft", to broaden keyword coverage.

DimensionReasoningScore

Specificity

Names the domain ("writing style contract for timeless, forceful English prose") and implies 1-2 concrete actions ("prose or rewrites"), but does not enumerate several specific capabilities, matching anchor 3 rather than the multi-action coverage of anchor 4.

3 / 5

Completeness

Explicitly answers both what ("A hard-edged writing style contract for timeless, forceful English prose without modern AI tics") and when ("Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone") with concrete trigger phrases, matching anchor 5.

5 / 5

Trigger Term Quality

Natural user terms like "prose", "rewrites", "clean", "AI cadence", "filler", and "therapeutic tone" give good keyword coverage, but common synonyms such as "writing", "editing", or "AI tone" are missing, so it sits at anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The anti-AI-cadence prose niche is clear and distinct, but "prose or rewrites" leaves minor overlap risk with generic writing/editing skills, placing it at anchor 4 rather than the fully distinct anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/beautiful-prose/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.